© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12297
    Prev
    Next
    INDEX
    Explanations

    drops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.70
     drops
    -0.59
     Drop
    -0.59
     drop
    -0.59
     DROP
    -0.59
    ]--;
    -0.59
    enumi
    -0.58
    ")){
    
    -0.57
    NameInMap
    -0.56
    '));
    
    -0.55
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
    HtmlAttribute
    0.63
    IUrlHelper
    0.61
    RectangleBorder
    0.59
     surla
    0.55
    canestro
    0.54
    cloudfront
    0.53
    tocin
    0.53
     PyLong
    0.52
     NIOS
    0.52
    Activations Density 0.125%

    No Known Activations